The object of the thesis is to design and validate an algorithm that is capable of predicting the effects of genetic mutations on protein functional level. Adopting these to further improve the understanding of genomic data on the level of signal transfers. The goal is round up some of the publicly available protein functional change prediction tools (i.e PolyPhen-2), applying them to the genomic data found in public databases (i. e. COSMIC), and validation of the results by comparing them to the consensus and also creating an automation to keep them up-to-date. The results collected by this process can be used to rank the available tools for specific tasks, and select the the best combination to predict functional effects. The operation of the system shall be tested on a chosen cell line's in silico model. By applying the predictions one-by-one and in combinations, observing how it affects signal transfer on a cellular level and using it to verify the usefulness of fine-tuning the method.